{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:42:42Z","timestamp":1770230562789,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":68,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609079","type":"print"},{"value":"9789819609086","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0908-6_15","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:24:23Z","timestamp":1733513063000},"page":"257-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["BiEfficient: Bidirectionally Prompting Vision-Language Models for\u00a0Parameter-Efficient Video Recognition"],"prefix":"10.1007","author":[{"given":"Haichen","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weibin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"15_CR2","unstructured":"Bahng, H., Jahanian, A., Sankaranarayanan, S., Isola, P.: Exploring visual prompts for adapting large-scale models. arXiv preprint arXiv:2203.17274 (2022)"},{"key":"15_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML. vol.\u00a02, p.\u00a04 (2021)"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Brattoli, B., Tighe, J., Zhdanov, F., Perona, P., Chalupka, K.: Rethinking zero-shot video classification: End-to-end training for realistic applications. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4613\u20134623 (2020)","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Huang, D.: Elaborative rehearsal for zero-shot action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 13638\u201313647 (2021)","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"15_CR6","first-page":"3468","volume":"2","author":"R Christoph","year":"2016","unstructured":"Christoph, R., Pinz, F.A.: Spatiotemporal residual networks for video action recognition. Adv. Neural. Inf. Process. Syst. 2, 3468\u20133476 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhang, T., Xu, C.: I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a033, pp. 8303\u20138311 (2019)","DOI":"10.1609\/aaai.v33i01.33018303"},{"issue":"2","key":"15_CR12","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., Qiao, Y.: Clip-adapter: Better vision-language models with feature adapters. Int. J. Comput. Vision 132(2), 581\u2013595 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Goswami, K., Karanam, S., Udhayanan, P., Joseph, K., Srinivasan, B.V.: Copl: Contextual prompt learning for vision-language understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 18090\u201318098 (2024)","DOI":"10.1609\/aaai.v38i16.29766"},{"key":"15_CR14","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)"},{"key":"15_CR15","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"15_CR16","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De\u00a0Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for nlp. In: International conference on machine learning. pp. 2790\u20132799. PMLR (2019)"},{"key":"15_CR17","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"15_CR18","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International conference on machine learning. pp. 4904\u20134916. PMLR (2021)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: European Conference on Computer Vision. pp. 105\u2013124. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"15_CR20","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision. pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"15_CR23","unstructured":"Li, K., Wang, Y., Peng, G., Song, G., Liu, Y., Li, H., Qiao, Y.: Uniformer: Unified transformer for efficient spatial-temporal representation learning. In: International Conference on Learning Representations (2021)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: Temporal excitation and aggregation for action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 909\u2013918 (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Lin, Z., Geng, S., Zhang, R., Gao, P., De\u00a0Melo, G., Wang, X., Dai, J., Qiao, Y., Li, H.: Frozen clip models are efficient video learners. In: European Conference on Computer Vision. pp. 388\u2013404. Springer (2022)","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., Hu, H.: Video swin transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, D., Wang, Y., Wang, L., Tai, Y., Wang, C., Li, J., Huang, F., Lu, T.: Teinet: Towards an efficient architecture for video recognition. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a034, pp. 11669\u201311676 (2020)","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., Lu, T.: Tam: Temporal adaptive module for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 13708\u201313718 (2021)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"15_CR31","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"15_CR32","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Ni, B., Peng, H., Chen, M., Zhang, S., Meng, G., Fu, J., Xiang, S., Ling, H.: Expanding language-image pretrained models for general video recognition. In: European Conference on Computer Vision. pp. 1\u201318. Springer (2022)","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"15_CR34","first-page":"26462","volume":"35","author":"J Pan","year":"2022","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: St-adapter: Parameter-efficient image-to-video transfer learning. Adv. Neural. Inf. Process. Syst. 35, 26462\u201326477 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Qin, J., Liu, L., Shao, L., Shen, F., Ni, B., Chen, J., Wang, Y.: Zero-shot action recognition with error-correcting output codes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 2833\u20132842 (2017)","DOI":"10.1109\/CVPR.2017.117"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Qing, Z., Zhang, S., Huang, Z., Wang, X., Wang, Y., Lv, Y., Gao, C., Sang, N.: Mar: Masked autoencoders for efficient action recognition. IEEE Transactions on Multimedia (2023)","DOI":"10.1109\/TMM.2023.3263288"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: proceedings of the IEEE International Conference on Computer Vision. pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"15_CR38","unstructured":"Quanfu\u00a0Fan, Richard\u00a0Chen, R.P.: Can an image classifier suffice for action recognition? In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"15_CR39","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"15_CR40","first-page":"12786","volume":"34","author":"M Ryoo","year":"2021","unstructured":"Ryoo, M., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: Adaptive space-time tokenization for videos. Adv. Neural. Inf. Process. Syst. 34, 12786\u201312797 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR41","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Advances in neural information processing systems 27 (2014)"},{"key":"15_CR42","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"15_CR43","first-page":"12991","volume":"35","author":"YL Sung","year":"2022","unstructured":"Sung, Y.L., Cho, J., Bansal, M.: Lst: Ladder side-tuning for parameter and memory efficient transfer learning. Adv. Neural. Inf. Process. Syst. 35, 12991\u201313005 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR44","first-page":"24193","volume":"34","author":"YL Sung","year":"2021","unstructured":"Sung, Y.L., Nair, V., Raffel, C.A.: Training neural networks with fixed sparse masks. Adv. Neural. Inf. Process. Syst. 34, 24193\u201324205 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision. pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"15_CR47","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: Tdn: Temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 1895\u20131904 (2021)","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van\u00a0Gool, L.: Temporal segment networks: Towards good practices for deep action recognition. In: European conference on computer vision. pp. 20\u201336. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"15_CR50","unstructured":"Wang, M., Xing, J., Liu, Y.: Actionclip: A new paradigm for video action recognition. arXiv preprint arXiv:2109.08472 (2021)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Q., Chen, K.: Alternative semantic representations for zero-shot human action recognition. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2017, Skopje, Macedonia, September 18\u201322, 2017, Proceedings, Part I 10. pp. 87\u2013102. Springer (2017)","DOI":"10.1007\/978-3-319-71249-9_6"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Wu, W., He, D., Lin, T., Li, F., Gan, C., Ding, E.: Mvfnet: Multi-view fusion network for efficient video recognition. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a035, pp. 2943\u20132951 (2021)","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Wu, W., Luo, H., Fang, B., Wang, J., Ouyang, W.: Cap4video: What can auxiliary captions do for text-video retrieval? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10704\u201310713 (2023)","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Wu, W., Sun, Z., Ouyang, W.: Revisiting classifier: Transferring vision-language models for video recognition. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a037, pp. 2847\u20132855 (2023)","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"15_CR56","doi-asserted-by":"crossref","unstructured":"Wu, W., Wang, X., Luo, H., Wang, J., Yang, Y., Ouyang, W.: Bidirectional cross-modal knowledge exploration for video recognition with pre-trained vision-language models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 6620\u20136630 (2023)","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV). pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"15_CR58","doi-asserted-by":"crossref","unstructured":"Xu, X., Hospedales, T.M., Gong, S.: Multi-task zero-shot action recognition with prioritised data augmentation. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14. pp. 343\u2013359. Springer (2016)","DOI":"10.1007\/978-3-319-46475-6_22"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, X., Arnab, A., Lu, Z., Zhang, M., Sun, C., Schmid, C.: Multiview transformers for video recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 3333\u20133343 (2022)","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"15_CR60","unstructured":"Yang, T., Zhu, Y., Xie, Y., Zhang, A., Chen, C., Li, M.: Aim: Adapting image models for efficient video understanding. In: International Conference on Learning Representations (2023)"},{"key":"15_CR61","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"15_CR62","unstructured":"Yuan, L., Chen, D., Chen, Y.L., Codella, N., Dai, X., Gao, J., Hu, H., Huang, X., Li, B., Li, C., et\u00a0al.: Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"15_CR63","unstructured":"Zaken, E.B., Ravfogel, S., Goldberg, Y.: Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)"},{"key":"15_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, R., Guo, Z., Zhang, W., Li, K., Miao, X., Cui, B., Qiao, Y., Gao, P., Li, H.: Pointclip: Point cloud understanding by clip. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8552\u20138562 (2022)","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Zhao, S., Zhu, L., Wang, X., Yang, Y.: Centerclip: Token clustering for efficient text-video retrieval. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 970\u2013981 (2022)","DOI":"10.1145\/3477495.3531950"},{"key":"15_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"15_CR67","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Long, Y., Guan, Y., Newsam, S., Shao, L.: Towards universal representation for unseen action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 9436\u20139445 (2018)","DOI":"10.1109\/CVPR.2018.00983"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:12:08Z","timestamp":1733515928000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}